SucheGood, Better, and Most Probable Recommendations
Machine Learning seems to offer the solution to the central problem in recommender systems: Learning to recommend interesting items from observations. However, one tends to run into similar problems each time one tries to apply out-of-the-box solutions from Machine Learning.
This article relates the problem of recommendation by user modeling closely to the machine learning problem and explicates some inherent dilemmas. A few examples will illustrate specific approaches and discuss underlying assumptions on the domain or how learned hypotheses relate to requirements on the user model. The article concludes with a tentative `checklist' that one might like to consider when thinking about to use Machine Learning in User Adaptive einvironments such as recommender systems.
Downloads:
- Good, Better, and Most Probable Recommendations - (2004-17.pdf, 826 KB)